More Like this

1. Adaptive Versioning in Transactional Memory Systems

   https://doi.org/10.3390/a14060171  

   Poudel, Pavan; Sharma, Gokarna (June 2021, Algorithms)

   Transactional memory has been receiving much attention from both academia and industry. In transactional memory, program code is split into transactions, blocks of code that appear to execute atomically. Transactions are executed speculatively and the speculative execution is supported through data versioning mechanism. Lazy versioning makes aborts fast but penalizes commits, whereas eager versioning makes commits fast but penalizes aborts. However, whether to use eager or lazy versioning to execute those transactions is still a hotly debated topic. Lazy versioning seems appropriate for write-dominated workloads and transactions in high contention scenarios whereas eager versioning seems appropriate for read-dominated workloads and transactions in low contention scenarios. This necessitates a priori knowledge on the workload and contention scenario to select an appropriate versioning method to achieve better performance. In this article, we present an adaptive versioning approach, called Adaptive, that dynamically switches between eager and lazy versioning at runtime, without the need of a priori knowledge on the workload and contention scenario but based on appropriate system parameters, so that the performance of a transactional memory system is always better than that is obtained using either eager or lazy versioning individually. We provide Adaptive for both persistent and non-persistent transactional memory systems using performance parameters appropriate for those systems. We implemented our adaptive versioning approach in the latest software transactional memory distribution TinySTM and extensively evaluated it through 5 micro-benchmarks and 8 complex benchmarks from STAMP and STAMPEDE suites. The results show significant benefits of our approach. Specifically, in persistent TM systems, our approach achieved performance improvements as much as 1.5× for execution time and as much as 240× for number of aborts, whereas our approach achieved performance improvements as much as 6.3× for execution time and as much as 170× for number of aborts in non-persistent transactional memory systems. 

   more » « less
2. Check-Wait-Pounce: Increasing Transactional Data Structure Throughput by Delaying Transactions

   https://doi.org/10.1007/978-3-030-22496-7_2  

   Lebanoff, Lance; Peterson, Christina; Dechev, Damian. (January 2019, IFIP International Conference on Distributed Applications and Interoperable Systems)

   Transactional data structures allow data structures to support transactional execution, in which a sequence of operations appears to execute atomically. We consider a paradigm in which a transaction commits its changes to the data structure only if all of its operations succeed; if one operation fails, then the transaction aborts. In this work, we introduce an optimization technique called Check-Wait-Pounce that increases performance by avoiding aborts that occur due to failed operations. Check-Wait-Pounce improves upon existing methodologies by delaying the execution of transactions until they are expected to succeed, using a thread-unsafe representation of the data structure as a heuristic. Our evaluation reveals that Check-Wait-Pounce reduces the number of aborts by an average of 49.0%. Because of this reduction in aborts, the tested transactional linked lists achieve average gains in throughput of 2.5x, while some achieve gains as high as 4x. 

   more » « less
3. Leveraging hardware TM in Haskell

   https://doi.org/10.1145/3293883.3295711  

   Yates, Ryan; Scott, Michael L. (January 2019, Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming)

   Transactional memory (TM) is heavily used for synchronization in the Haskell programming language, but its performance has historically been poor. We set out to improve this performance using hardware TM (HTM) on Intel processors. This task is complicated by Haskell's retry mechanism, which requires information to escape aborted transactions, and by the heavy use of indirection in the Haskell runtime, which means that even small transactions are likely to over-flow hardware buffers. It is eased by functional semantics, which preclude irreversible operations; by the static separation of transactional state, which precludes privatization; and by the error containment of strong typing, which enables so-called lazy subscription to the lock that protects the "fallback" code path. We describe a three-level hybrid TM system for the Glasgow Haskell Compiler (GHC). Our system first attempts to perform an entire transaction in hardware. Failing that, it falls back to software tracking of read and write sets combined with a commit-time hardware transaction. If necessary, it employs a global lock to serialize commits (but still not the bodies of transactions). To get good performance from hardware TM while preserving Haskell semantics, we use Bloom filters for read and write set tracking. We also implemented and extended the newly proposed mutable constructor fields language feature to significantly reduce indirection. Experimental results with complex data structures show significant improvements in throughput and scalability. 

   more » « less
4. NOMAD: Non-Exclusive Memory Tiering via Transactional Page Migration

   Xinag, Lingfeng; Lin, Zhen; Deng, Weishu Deng; Lu, Hui; Rao, Jia; Yuan, Yifan Yuan; Wang, Ren (July 2024, The 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI'24))

   With the advent of byte-addressable memory devices, such as CXL memory, persistent memory, and storage-class memory, tiered memory systems have become a reality. Page migration is the de facto method within operating systems for managing tiered memory. It aims to bring hot data whenever possible into fast memory to optimize the performance of data accesses while using slow memory to accommodate data spilled from fast memory. While the existing research has demonstrated the effectiveness of various optimizations on page migration, it falls short of addressing a fundamental question: Is exclusive memory tiering, in which a page is either present in fast memory or slow memory, but not both simultaneously, the optimal strategy for tiered memory management? We demonstrate that page migration-based exclusive memory tiering suffers significant performance degradation when fast memory is under pressure. In this paper, we propose nonexclusive memory tiering, a page management strategy that retains a copy of pages recently promoted from slow memory to fast memory to mitigate memory thrashing. To enable non-exclusive memory tiering, we develop NOMAD, a new page management mechanism for Linux that features transactional page migration and page shadowing. NOMAD helps remove page migration off the critical path of program execution and makes migration completely asynchronous. Evaluations with carefully crafted micro-benchmarks and real-world applications show that NOMAD is able to achieve up to 6x performance improvement over the state-of-the-art transparent page placement (TPP) approach in Linux when under memory pressure. We also compare NOMAD with a recently proposed hardware-assisted, access sampling-based page migration approach and demonstrate NOMAD’s strengths and potential weaknesses in various scenarios. 

   more » « less
5. Nomad: Non-Exclusive Memory Tiering via Transactional Page Migration

   Xiang, Lingfeng; Lin, Zhen; Deng, Weishu; Lu, Hui; Rao, Jia Rao; Yuan, Yifan; Wang, Ren (July 2024, The Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI'24).)

   With the advent of byte-addressable memory devices, such as CXLmemory, persistent memory, and storage-class memory, tiered memory systems have become a reality. Page migration is the de facto method within operating systems for managing tiered memory. It aims to bring hot data whenever possible into fast memory to optimize the performance of data accesses while using slow memory to accommodate data spilled from fast memory. While the existing research has demonstrated the effectiveness of various optimizations on page migration, it falls short of addressing a fundamental question: Is exclusive memory tiering, in which a page is either present in fast memory or slow memory, but not both simultaneously, the optimal strategy for tiered memory management? We demonstrate that page migration-based exclusive memory tiering suffers significant performance degradation when fast memory is under pressure. In this paper, we propose nonexclusive memory tiering, a page management strategy that retains a copy of pages recently promoted from slow memory to fast memory to mitigate memory thrashing. To enable non-exclusive memory tiering, we develop NOMAD, a new page management mechanism for Linux that features transactional page migration and page shadowing. NOMAD helps remove page migration off the critical path of program execution and makes migration completely asynchronous. Evaluations with carefully crafted micro-benchmarks and real-world applications show that NOMAD is able to achieve up to 6x performance improvement over the state-of-the-art transparent page placement (TPP) approach in Linux when under memory pressure. We also compare NOMAD with a recently proposed hardware-assisted, access sampling-based page migration approach and demonstrate NOMAD’s strengths and potential weaknesses in various scenarios. 

   more » « less